{
    "info": {
        "author": "Bogdan Kulynych, Mohammad Yaghini",
        "author_email": "hello@bogdankulynych.me, mohammad.yaghini@epfl.ch",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "Intended Audience :: Developers",
            "License :: OSI Approved :: MIT License",
            "Natural Language :: English",
            "Operating System :: OS Independent",
            "Programming Language :: Python",
            "Programming Language :: Python :: 3",
            "Programming Language :: Python :: 3.4",
            "Programming Language :: Python :: 3.5",
            "Programming Language :: Python :: 3.6",
            "Programming Language :: Python :: Implementation :: CPython",
            "Topic :: Scientific/Engineering :: Artificial Intelligence",
            "Topic :: Software Development :: Libraries :: Python Modules"
        ],
        "description": "###\nmia\n###\n\n|pypi| |license| |build_status| |docs_status| |zenodo|\n\n.. |pypi| image:: https://img.shields.io/pypi/v/mia.svg\n   :target: https://pypi.org/project/mia/\n   :alt: PyPI version\n\n.. |build_status| image:: https://travis-ci.org/spring-epfl/mia.svg?branch=master\n   :target: https://travis-ci.org/spring-epfl/mia\n   :alt: Build status\n\n.. |docs_status| image:: https://readthedocs.org/projects/mia-lib/badge/?version=latest\n   :target: https://mia-lib.readthedocs.io/?badge=latest\n   :alt: Documentation status\n\n.. |license| image:: https://img.shields.io/pypi/l/mia.svg\n   :target: https://pypi.org/project/mia/\n   :alt: License\n\n.. |zenodo| image:: https://zenodo.org/badge/DOI/10.5281/zenodo.1433744.svg\n   :target: https://zenodo.org/record/1433744\n   :alt: Citing with the Zenodo\n\nA library for running membership inference attacks (MIA) against machine learning models. Check out\nthe `documentation <https://mia-lib.rtfd.io>`_.\n\n.. description-marker-do-not-remove\n\nThese are attacks against privacy of the training data. In MIA, an attacker tries to guess whether a\ngiven example was used during training of a target model or not, only by querying the model. See\nmore in the paper by `Shokri et al <https://arxiv.org/abs/1610.05820>`_. Currently, you can use the\nlibrary to evaluate the robustness of your Keras or PyTorch models to MIA.\n\nFeatures:\n\n* Implements the original shadow model `attack <https://arxiv.org/abs/1610.05820>`_\n* Is customizable, can use any scikit learn's ``Estimator``-like object as a shadow or attack model\n* Is tested with Keras and PyTorch\n\n.. getting-started-marker-do-not-remove\n\n===============\nGetting started\n===============\n\nYou can install mia from PyPI:\n\n.. code-block::  bash\n\n    pip install mia\n\n.. usage-marker-do-not-remove\n\n=====\nUsage \n=====\n\nShokri et al. attack\n====================\n\nSee the `full runnable example\n<https://github.com/spring-epfl/mia/tree/master/examples/cifar10.py>`_.  Read the details of the\nattack in the `paper <https://arxiv.org/abs/1610.05820>`_.\n\nLet ``target_model_fn()`` return the target model architecture as a scikit-like classifier. The\nattack is white-box, meaning the attacker is assumed to know the architecture. Let ``NUM_CLASSES``\nbe the number of classes of the classification problem.\n\nFirst, the attacker needs to train several *shadow models* \u2014that mimick the target model\u2014\non different datasets sampled from the original data distribution. The following code snippet\ninitializes a *shadow model bundle*, and runs the training of the shadows. For each shadow model,\n``2 * SHADOW_DATASET_SIZE`` examples are sampled without replacement from the full attacker's\ndataset.  Half of them will be used for control, and the other half for training of the shadow model.\n\n.. code-block::  python\n\n    from mia.estimators import ShadowModelBundle\n\n    smb = ShadowModelBundle(\n        target_model_fn,\n        shadow_dataset_size=SHADOW_DATASET_SIZE,\n        num_models=NUM_MODELS,\n    )\n    X_shadow, y_shadow = smb.fit_transform(attacker_X_train, attacker_y_train)\n\n``fit_transform`` returns *attack data* ``X_shadow, y_shadow``. Each row in ``X_shadow`` is a\nconcatenated vector consisting of the prediction vector of a shadow model for an example from the\noriginal dataset, and the example's class (one-hot encoded). Its shape is hence ``(2 *\nSHADOW_DATASET_SIZE, 2 * NUM_CLASSES)``. Each label in ``y_shadow`` is zero if a corresponding\nexample was \"out\" of the training dataset of the shadow model (control), or one, if it was \"in\" the\ntraining.\n\nmia provides a class to train a bundle of attack models, one model per class. ``attack_model_fn()``\nis supposed to return a scikit-like classifier that takes a vector of model predictions ``(NUM_CLASSES, )``,\nand returns whether an example with these predictions was in the training, or out.\n\n.. code-block::  python\n\n    from mia.estimators import AttackModelBundle\n\n    amb = AttackModelBundle(attack_model_fn, num_classes=NUM_CLASSES)\n    amb.fit(X_shadow, y_shadow)\n\nIn place of the ``AttackModelBundle`` one can use any binary classifier that takes ``(2 *\nNUM_CLASSES, )``-shape examples (as explained above, the first half of an input is the prediction\nvector from a model, the second half is the true class of a corresponding example).\n\nTo evaluate the attack, one must encode the data in the above-mentioned format. Let ``target_model`` be\nthe target model, ``data_in`` the data (tuple ``X, y``) that was used in the training of the target model, and\n``data_out`` the data that was not used in the training.\n\n.. code-block::  python\n\n    from mia.estimators import prepare_attack_data    \n\n    attack_test_data, real_membership_labels = prepare_attack_data(\n        target_model, data_in, data_out\n    )\n\n    attack_guesses = amb.predict(attack_test_data)\n    attack_accuracy = np.mean(attack_guesses == real_membership_labels)\n\n.. misc-marker-do-not-remove\n\n======\nCiting\n======\n\n.. code-block::\n\n   @misc{mia,\n     author       = {Bogdan Kulynych and\n                     Mohammad Yaghini},\n     title        = {{mia: A library for running membership inference \n                      attacks against ML models}},\n     month        = sep,\n     year         = 2018,\n     doi          = {10.5281/zenodo.1433744},\n     url          = {https://doi.org/10.5281/zenodo.1433744}\n   }\n\n\n\n",
        "description_content_type": "",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/spring-epfl/mia",
        "keywords": "",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "mia",
        "package_url": "https://pypi.org/project/mia/",
        "platform": "",
        "project_url": "https://pypi.org/project/mia/",
        "project_urls": {
            "Homepage": "https://github.com/spring-epfl/mia"
        },
        "release_url": "https://pypi.org/project/mia/0.1.2/",
        "requires_dist": [
            "numpy",
            "scipy",
            "scikit-learn",
            "torch",
            "tqdm",
            "pytest; extra == 'dev'",
            "pytest-lazy-fixture; extra == 'dev'",
            "tensorflow; extra == 'dev'",
            "skorch; extra == 'dev'",
            "keras; extra == 'dev'",
            "sphinx; extra == 'dev'",
            "sphinx-rtd-theme; extra == 'dev'",
            "black; extra == 'dev'",
            "pytest; extra == 'test'",
            "pytest-lazy-fixture; extra == 'test'",
            "tensorflow; extra == 'test'",
            "skorch; extra == 'test'",
            "keras; extra == 'test'"
        ],
        "requires_python": "",
        "summary": "A library for running membership inference attacks against ML models",
        "version": "0.1.2"
    },
    "last_serial": 4315812,
    "releases": {
        "0.1.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "177bf610890a7d3c60d1cc66830e65ae",
                    "sha256": "40a6cd9a74099033e8216ed01d07f64c2af0d599eea28d96e837682d44153798"
                },
                "downloads": -1,
                "filename": "mia-0.1.1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "177bf610890a7d3c60d1cc66830e65ae",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 10142,
                "upload_time": "2018-09-23T18:28:13",
                "url": "https://files.pythonhosted.org/packages/e8/1b/232e9de9f96887d1c7add2a3226ca02f2e3ea5c1c92803e833bbd405720f/mia-0.1.1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "52a1ac440fcdcfb7fd720aea27b272a0",
                    "sha256": "33de8d5e9246d2ac2cab55ead798cd39c42fb6fcc7a009f0464ca4a95f87bb64"
                },
                "downloads": -1,
                "filename": "mia-0.1.1.tar.gz",
                "has_sig": false,
                "md5_digest": "52a1ac440fcdcfb7fd720aea27b272a0",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 15890,
                "upload_time": "2018-09-23T18:28:15",
                "url": "https://files.pythonhosted.org/packages/e1/cb/2b2ba3712896fd293fe58c34a2d00ac178c25b85263c7632448f8bc75517/mia-0.1.1.tar.gz"
            }
        ],
        "0.1.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "684eaac8c7d551bf2d48c1210dcc0916",
                    "sha256": "f170384300f1e08898237cf7f43582fb2b95c0ea1ac56c2c8198e18f58633154"
                },
                "downloads": -1,
                "filename": "mia-0.1.2-py2-none-any.whl",
                "has_sig": false,
                "md5_digest": "684eaac8c7d551bf2d48c1210dcc0916",
                "packagetype": "bdist_wheel",
                "python_version": "py2",
                "requires_python": null,
                "size": 13470,
                "upload_time": "2018-09-27T11:00:15",
                "url": "https://files.pythonhosted.org/packages/ff/2c/9027be252e23650230be310f9b7886fc2f9f5bed77afe89542441a44c8ce/mia-0.1.2-py2-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "ea7ab0440a729e549018171836ee3fc2",
                    "sha256": "118606dfe9f8cbd8ecb6edcd1231d5360decbf4ff02d90a1696df73958580a55"
                },
                "downloads": -1,
                "filename": "mia-0.1.2.tar.gz",
                "has_sig": false,
                "md5_digest": "ea7ab0440a729e549018171836ee3fc2",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 17240,
                "upload_time": "2018-09-27T11:00:17",
                "url": "https://files.pythonhosted.org/packages/7d/12/f149a7cd43e49725921e9884363aa3cbfea8a49c319a944eb71d48973fa9/mia-0.1.2.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "684eaac8c7d551bf2d48c1210dcc0916",
                "sha256": "f170384300f1e08898237cf7f43582fb2b95c0ea1ac56c2c8198e18f58633154"
            },
            "downloads": -1,
            "filename": "mia-0.1.2-py2-none-any.whl",
            "has_sig": false,
            "md5_digest": "684eaac8c7d551bf2d48c1210dcc0916",
            "packagetype": "bdist_wheel",
            "python_version": "py2",
            "requires_python": null,
            "size": 13470,
            "upload_time": "2018-09-27T11:00:15",
            "url": "https://files.pythonhosted.org/packages/ff/2c/9027be252e23650230be310f9b7886fc2f9f5bed77afe89542441a44c8ce/mia-0.1.2-py2-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "ea7ab0440a729e549018171836ee3fc2",
                "sha256": "118606dfe9f8cbd8ecb6edcd1231d5360decbf4ff02d90a1696df73958580a55"
            },
            "downloads": -1,
            "filename": "mia-0.1.2.tar.gz",
            "has_sig": false,
            "md5_digest": "ea7ab0440a729e549018171836ee3fc2",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 17240,
            "upload_time": "2018-09-27T11:00:17",
            "url": "https://files.pythonhosted.org/packages/7d/12/f149a7cd43e49725921e9884363aa3cbfea8a49c319a944eb71d48973fa9/mia-0.1.2.tar.gz"
        }
    ]
}